Sinhala_Bert_Finetune_BS8_LR5e-5

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1651
• Bleu: 0.4158

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
5.7138	1.0	225	2.5467	4.4630
3.1683	2.0	450	1.6767	18.1022
2.2024	3.0	675	1.3708	25.4629
1.6300	4.0	900	1.1976	41.7703
1.0056	5.0	1125	1.1782	39.8555
0.7387	6.0	1350	1.1153	44.6256
0.5578	7.0	1575	1.1164	41.9795
0.4116	8.0	1800	1.0800	40.4000

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2